English
Related papers

Related papers: Exploring and Improving Drafts in Blockwise Parall…

200 papers

Large Language Models (LLMs) exhibit high inference latency due to their autoregressive decoding nature. While the draft head in speculative decoding mitigates this issue, its full potential remains unexplored. In this paper, we introduce…

Computation and Language · Computer Science 2024-08-16 Kaiqi Zhang , Jing Zhao , Rui Chen

Speculative decoding accelerates LLM inference by having a small drafter propose tokens that a larger target model verifies in parallel. Recent diffusion-based parallel drafters such as DFlash predict the full B-token block in one forward…

Machine Learning · Computer Science 2026-05-20 Tianyu Wu , Yu Yao , Zhenting Qi , Han Zheng , Zhuohan Wang , Haoran Ma , Lawrence Liao , Himabindu Lakkaraju , Ju Li , Yilun Du

Transformers excel in Natural Language Processing (NLP) due to their prowess in capturing long-term dependencies but suffer from exponential resource consumption with increasing sequence lengths. To address these challenges, we propose MCSD…

Computation and Language · Computer Science 2024-07-12 Hua Yang , Duohai Li , Shiman Li

Speculative decoding accelerates inference in large language models (LLMs) by generating multiple draft tokens simultaneously. However, existing methods often struggle with token misalignment between the training and decoding phases,…

Computation and Language · Computer Science 2025-10-21 Shijing Hu , Jingyang Li , Xingyu Xie , Zhihui Lu , Kim-Chuan Toh , Pan Zhou

We propose TPP-SD, a novel approach that accelerates Transformer temporal point process (TPP) sampling by adapting speculative decoding (SD) techniques from language models. By identifying the structural similarities between thinning…

Machine Learning · Computer Science 2025-10-22 Shukai Gong , Yiyang Fu , Fengyuan Ran , Quyu Kong , Feng Zhou

Multi-path speculative decoding accelerates lossless sampling from a target model by using a cheaper draft model to generate a draft tree of tokens, and then applies a verification algorithm that accepts a subset of these. While prior work…

Machine Learning · Computer Science 2026-02-20 Rahul Thomas , Teo Kitanovski , Micah Goldblum , Arka Pal

Block Diffusion Models (BDMs) support parallel generation, flexible-length output, and KV caching, making them promising for efficient document parsing. However, existing BDMs bind denoising and cache commitment to fixed block boundaries:…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Mingxu Chai , Ziyu Shen , Chenyu Liu , Kaidi Zhang , Jiazheng Zhang , Dingwei Zhu , Zhiheng Xi , Ruoyu Chen , Jun Long , Jihua Kang , Tao Gui , Qi Zhang

Reasoning training incentivizes LLMs to produce long chains of thought (long CoT), which among other things, allows them to explore solution strategies with self-checking. This results in higher accuracy, but inflates context length,…

Speculative decoding has rapidly emerged as a leading approach for accelerating language model (LM) inference, as it offers substantial speedups while yielding identical outputs. This relies upon a small draft model, tasked with predicting…

Computation and Language · Computer Science 2026-02-17 Miles Williams , Young D. Kwon , Rui Li , Alexandros Kouris , Stylianos I. Venieris

Speculative decoding accelerates large language model inference using a smaller draft model. In this paper, we establish a surprising connection between speculative decoding and channel simulation, which aims at simulating a noisy channel…

Computation and Language · Computer Science 2025-04-23 Szymon Kobus , Deniz Gündüz

We present speculative sampling, an algorithm for accelerating transformer decoding by enabling the generation of multiple tokens from each transformer call. Our algorithm relies on the observation that the latency of parallel scoring of…

Computation and Language · Computer Science 2023-02-03 Charlie Chen , Sebastian Borgeaud , Geoffrey Irving , Jean-Baptiste Lespiau , Laurent Sifre , John Jumper

Speculative Decoding (SD) is a widely used approach to accelerate the inference of large language models (LLMs) without reducing generation quality. It operates by first using a compact model to draft multiple tokens efficiently, followed…

Computation and Language · Computer Science 2025-08-08 Hossein Entezari Zarch , Lei Gao , Chaoyi Jiang , Murali Annavaram

With the increasingly giant scales of (causal) large language models (LLMs), the inference efficiency comes as one of the core concerns along the improved performance. In contrast to the memory footprint, the latency bottleneck seems to be…

Computation and Language · Computer Science 2024-04-24 Chen Zhang , Zhuorui Liu , Dawei Song

We present Recurrent Drafter (ReDrafter), an advanced speculative decoding approach that achieves state-of-the-art speedup for large language models (LLMs) inference. The performance gains are driven by three key aspects: (1) leveraging a…

Computation and Language · Computer Science 2024-12-17 Yunfei Cheng , Aonan Zhang , Xuanyu Zhang , Chong Wang , Yi Wang

Most large language models are autoregressive: they generate tokens one at a time. Discrete diffusion language models can generate multiple tokens in parallel, but sampling from them requires a denoising order: a strategy for deciding which…

Artificial Intelligence · Computer Science 2026-03-27 Daniel Israel , Tian Jin , Ellie Cheng , Guy Van den Broeck , Aditya Grover , Suvinay Subramanian , Michael Carbin

Speculative decoding accelerates LLM inference by using a smaller draft model to speculate tokens that a larger target model verifies. Verification is often the bottleneck (e.g. verification is $4\times$ slower than token generation when a…

Computation and Language · Computer Science 2026-05-27 Avinash Kumar , Sujay Sanghavi , Poulami Das

Existing speculative decoding methods typically require additional model structure and training processes to assist the model for draft token generation. This makes the migration of acceleration methods to the new model more costly and more…

Computation and Language · Computer Science 2024-10-08 Yixuan Wang , Xianzhen Luo , Fuxuan Wei , Yijun Liu , Qingfu Zhu , Xuanyu Zhang , Qing Yang , Dongliang Xu , Wanxiang Che

This research aims to accelerate the inference speed of large language models (LLMs) with billions of parameters. We propose \textbf{S}mart \textbf{P}arallel \textbf{A}uto-\textbf{C}orrect d\textbf{E}coding (SPACE), an innovative approach…

Computation and Language · Computer Science 2024-05-21 Hanling Yi , Feng Lin , Hongbin Li , Peiyang Ning , Xiaotian Yu , Rong Xiao

Speculative decoding accelerates autoregressive generation by letting a lightweight draft model propose future tokens that a larger target model then verifies in parallel. In practice, however, draft models are usually trained on broad…

Computation and Language · Computer Science 2026-03-31 Mohamad Zbib , Mohamad Bazzi , Ammar Mohanna , Hasan Abed Al Kader Hammoud , Bernard Ghanem

The emergence of long-context large language models (LLMs) offers a promising alternative to traditional retrieval-augmented generation (RAG) for processing extensive documents. However, the computational overhead of long-context inference…

Computation and Language · Computer Science 2025-06-24 Guanzheng Chen , Qilong Feng , Jinjie Ni , Xin Li , Michael Qizhe Shieh
‹ Prev 1 8 9 10 Next ›